Commit History
-
Added .gitattributes and .gitignore files
Abhishek Gola3cc26e7
-
Added back lfs files
Abhishek Golab373a5f
-
Update README.md (#276)
adding paper source & citation Co-authored-by: Yuantao Feng <yuantao.feng@opencv.org.cn>28faf34
-
[GSoC] Add block quantized models (#270)
* Gemm and MatMul block quantization support * refactoring * fix indentation * node name independent * Block quantization tool: - constant weight category supported - add data type saturation - handled the case in which all the elements within a block are the same benchmark script modified to support block quantized models block quantized some models * add missing block quantized models * formatting * add blocked models to eval script. Evaluation yunet * Add sface and pphumanseg evaluation, block quantization tool fix, handpose blocked model fix, removed blocked CRNN EN, * changed evaluation metric in block_quantize script and add verbose mode * Add evaluation for PP-ResNet and Mobilenet * changed file suffix and update readmes * renamed int8bq855ea33
-
fixing bug crashing eval on widerface (#267)
TonyCongqianWang +1: Tony WangCo-authored-by: Tony Wang <Tony.Wang@mabri.vision>489de70
-
bump opencv version to 4.10.0 (#260)
* bump opencv version to 4.10.0 * doc: version change * fix version control * fix version control for efficient samf0ac01e
-
Fix spelling, spacing, and unused variables (#236)
Ryan Lee* Fix spelling, spacing, and unused variables * Fixed typo in 3 more models * Added open back * Remove setBackendAndTarget functions from C++ demos, which are unused functionality.71b890b
-
Bump version 4.9 (#222)
* update benchmark results on i7-12700K * update benchmark results on edge2 * add benchmark results on Horizon Sunrise X3 PI * add benchmark results on Jetson Nano B01 (CPU) * add benchmark results on Raspberry Pi 4B * add benchmark results on Jetson Nano B01 (GPU) * add MAIX-III and StarFive benchmark results * update benchmark results on Khadas VIM3 * update hardware setup info * bump opencv version requirement to 4.9.0 * update benchmark results on RV1126 * regenerate table * change * to x in input size text * regenerate table * rollback for '\\*' * regenerate table * add description for atlas 200i dk a2 * tune table --------- Co-authored-by: Wanli <wanli.zhong.1999@gmail.com>a683633
-
fix nontype error (#215)
9869cb3
-
bump version to 4.8.0 (#190)
* bump version to 4.8.0 * update benchmark results on i7 & rpi * correct python command on i7 * update results on jetson nano * update results on atlas 200 cpu * update results on vim3 cpu, sunrise x3 cpu * update results on vim3 npu * update results on edge2 * update results on rv1126 and vision2 * update results on axp * update table90429ca
-
Add back example output images as lfs tracked files (#166)
* lfs track images now * add back example images * modify paths * modify paths part 2 * correct paths in each model's readme32c4d08
-
update yunet to v2 (#151)
Wwupup60c396d -
update and modify documentation (#161)
Wanli4ae02a3
-
Limit combinations of backends and targets in demos and benchmark (#145)
* limit backend and target combination in demos and benchmark * simpler version checkingc6644c1
-
add Yunet C++ demo (#138)
* add cpp demo for yunet * add a new line before end of file * new line before eoffe1df9a
-
update doc of yunet with specification of detectable face sizes (#118)
ee1241e
-
Merge pull request #95 from Satgoy152:adding-doc
Satyam GoyalImproved help messages for demo programs (#95) - Added Demo Documentation - Updated help messages - Changed exception link84680ed
-
Add script to evaluate face detection by WIDERFace (#70)
Wanli* Add script to evaluate face detection by WIDERFace * add the result of YuNet874f143
-
Add example outputs and display in README (#59)
* add demo images * add demo to readme70465c1
-
Use YuNet of fixed input shape to avoid 'parseShape' error (#45)
* replace with yunet of fixed input shape * update quantized yunet * update yunet filename used in scripts * add a note message for https://github.com/opencv/opencv_zoo/issues/44e77fe84
-
Add options for demo scripts to select backend & targets (#43)
* add options for selecting backend & targets * add eoledcfc33
-
Update ONNX opset version of YuNet to 11 for quantization (#34)
Yuantao Feng* update ONNX opset version of YuNet to 11 for quantization * fix corruption when face detection results is nonea524e9b
-
correct default values of model filenames in demo scripts (#11)
Yuantao Fengfb84dfb
-
Renaming model files to have more information on architecture, training data and more (#7)
Yuantao Feng* add suffix of training dataset, arch & upload time to each model * update DB-IC15 benchmark resultse9dd5ad
-
Update to OpenCV APIs (YuNet -> FaceDetectorYN, SFace -> FaceRecognizerSF) (#6)
Yuantao Feng* update YuNet and SFace impl with opencv-python api39e569f
-
Add SFace for face recognition (#3)
Yuantao Feng* SFace and demo impl * benchmark support and results for SFace5ac585d
-
Benchmark framework implementation and 3 models added:
fengyuentau* benchmark framework: benchmarks based on configs * added impl and benchmark for YuNet (face detection) * added impl and benchmark for DB (text detection) * added impl and benchmark for CRNN (text recognition)ce28923